changeset 0:f2757ab26483 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/blob/master/tool_collections/kraken/kraken_report/ commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
author devteam
date Thu, 23 Jul 2015 10:56:14 -0400
parents
children 688428f6800f
files README.rst kraken-mpa-report.xml kraken-report.xml macros.xml tool-data/kraken_databases.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml
diffstat 6 files changed, 256 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README.rst	Thu Jul 23 10:56:14 2015 -0400
@@ -0,0 +1,92 @@
+Introduction
+============
+
+`Kraken <http://ccb.jhu.edu/software/kraken/>`__ is a taxonomic sequence
+classifier that assigns taxonomic labels to short DNA reads. It does
+this by examining the :math:`k`-mers within a read and querying a
+database with those :math:`k`-mers. This database contains a mapping of
+every :math:`k`-mer in
+`Kraken <http://ccb.jhu.edu/software/kraken/>`__'s genomic library to
+the lowest common ancestor (LCA) in a taxonomic tree of all genomes that
+contain that :math:`k`-mer. The set of LCA taxa that correspond to the
+:math:`k`-mers in a read are then analyzed to create a single taxonomic
+label for the read; this label can be any of the nodes in the taxonomic
+tree. `Kraken <http://ccb.jhu.edu/software/kraken/>`__ is designed to be
+rapid, sensitive, and highly precise. Our tests on various real and
+simulated data have shown
+`Kraken <http://ccb.jhu.edu/software/kraken/>`__ to have sensitivity
+slightly lower than Megablast with precision being slightly higher. On a
+set of simulated 100 bp reads,
+`Kraken <http://ccb.jhu.edu/software/kraken/>`__ processed over 1.3
+million reads per minute on a single core in normal operation, and over
+4.1 million reads per minute in quick operation.
+
+The latest released version of Kraken will be available at the `Kraken
+website <http://ccb.jhu.edu/software/kraken/>`__, and the latest updates
+to the Kraken source code are available at the `Kraken GitHub
+repository <https://github.com/DerrickWood/kraken>`__.
+
+If you use `Kraken <http://ccb.jhu.edu/software/kraken/>`__ in your
+research, please cite the `Kraken
+paper <http://genomebiology.com/2014/15/3/R46>`__. Thank you!
+
+System Requirements
+===================
+
+Note: Users concerned about the disk or memory requirements should read
+the paragraph about MiniKraken, below.
+
+-  **Disk space**: Construction of Kraken's standard database will
+   require at least 160 GB of disk space. Customized databases may
+   require more or less space. Disk space used is linearly proportional
+   to the number of distinct :math:`k`-mers; as of Feb. 2015, Kraken's
+   default database contains just under 6 billion (6e9) distinct
+   :math:`k`-mers.
+
+   In addition, the disk used to store the database should be
+   locally-attached storage. Storing the database on a network
+   filesystem (NFS) partition can cause Kraken's operation to be very
+   slow, or to be stopped completely. As NFS accesses are much slower
+   than local disk accesses, both preloading and database building will
+   be slowed by use of NFS.
+
+-  **Memory**: To run efficiently, Kraken requires enough free memory to
+   hold the database in RAM. While this can be accomplished using a
+   ramdisk, Kraken supplies a utility for loading the database into RAM
+   via the OS cache. The default database size is 75 GB (as of Feb.
+   2015), and so you will need at least that much RAM if you want to
+   build or run with the default database.
+
+-  **Dependencies**: Kraken currently makes extensive use of Linux
+   utilities such as sed, find, and wget. Many scripts are written using
+   the Bash shell, and the main scripts are written using Perl. Core
+   programs needed to build the database and run the classifier are
+   written in C++, and need to be compiled using g++. Multithreading is
+   handled using OpenMP. Downloads of NCBI data are performed by wget
+   and in some cases, by rsync. Most Linux systems that have any sort of
+   development package installed will have all of the above listed
+   programs and libraries available.
+
+   Finally, if you want to build your own database, you will need to
+   install the
+   `Jellyfish <http://www.cbcb.umd.edu/software/jellyfish/>`__
+   :math:`k`-mer counter. Note that Kraken only supports use of
+   Jellyfish version 1. Jellyfish version 2 is not yet compatible with
+   Kraken.
+
+-  **Network connectivity**: Kraken's standard database build and
+   download commands expect unfettered FTP and rsync access to the NCBI
+   FTP server. If you're working behind a proxy, you may need to set
+   certain environment variables (such as ``ftp_proxy`` or
+   ``RSYNC_PROXY``) in order to get these commands to work properly.
+
+-  **MiniKraken**: To allow users with low-memory computing environments
+   to use Kraken, we supply a reduced standard database that can be
+   downloaded from the Kraken web site. When Kraken is run with a
+   reduced database, we call it MiniKraken.
+
+   The database we make available is only 4 GB in size, and should run
+   well on computers with as little as 8 GB of RAM. Disk space required
+   for this database is also only 4 GB.
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/kraken-mpa-report.xml	Thu Jul 23 10:56:14 2015 -0400
@@ -0,0 +1,71 @@
+<tool id="kraken-mpa-report" name="Kraken-mpa-report" version="1.1.0">
+  <expand macro="version_command" />
+  <expand macro="requirements" />
+  <expand macro="stdio" />
+  <description>
+        view report of classification for multiple samples
+    </description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <command>
+      <![CDATA[
+
+#for $input_count, $input_classification in enumerate( $classification ):
+ ln -s "${input_classification}" "sample_${input_count}" &&
+#end for
+
+kraken-mpa-report @INPUT_DATABASE@
+
+#for $input_count, $input_classification in enumerate( $classification ):
+ "sample_${input_count}"
+#end for
+
+${show_zeros}
+${header_line}
+
+> "$output_report"
+
+
+	]]>
+    </command>
+    <inputs>
+      <param multiple="True" name="classification" type="data" format="tabular" label="Kraken output"/>
+      <param name="show_zeros" type="boolean" truevalue="--show-zeros" falsevalue="" checked="False" label="Display taxa even if they lack a read in any sample" help="--show-zeros"/>
+      <param name="header_line" type="boolean" truevalue="--header-line" falsevalue="" checked="False" label="Display a header line indicating sample IDs" help="--header-line"/>
+        <expand macro="input_database" />
+    </inputs>
+    <outputs>
+        <data format="tabular" name="output_report" />
+    </outputs>
+    <help>
+<![CDATA[
+
+.. class:: warningmark
+
+**Note**: the database used must be the same as the one used in the original Kraken run
+
+-----
+
+**What is Does**
+
+Kraken-mpa-report summarizes read counts across taxonomic ranks for multiple samples. This is convenient for comparing results across multiple expreriments, conditions, locations, etc. It support sthe following parameters::
+
+ --show-zeros    Display taxa even if they lack a read in any sample
+ --header-line   Display a header line indicating sample IDs
+                 (sample IDs are the filenames)
+
+-----
+
+**Output**
+
+The output of kraken-mpa-report is tab-delimited, with one line per taxon.
+
+
+
+
+
+    ]]>
+    </help>
+    <expand macro="citations" />
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/kraken-report.xml	Thu Jul 23 10:56:14 2015 -0400
@@ -0,0 +1,49 @@
+<tool id="kraken-report" name="Kraken-report" version="1.1.0">
+    <description>
+        view a sample report of your classification
+    </description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <command>
+        <![CDATA[
+        @SET_DATABASE_PATH@ &&
+        kraken-report @INPUT_DATABASE@ "${kraken_output}" > "$output_report"
+        ]]>
+    </command>
+    <inputs>
+        <param format="tabular" label="Kraken output" name="kraken_output" type="data" help="Select taxonomy classification produced by kraken"/>
+        <expand macro="input_database" />
+    </inputs>
+    <outputs>
+        <data format="tabular" name="output_report" />
+    </outputs>
+    <help>
+<![CDATA[
+
+.. class:: warningmark
+
+**Note**: the database used must be the same as the one used in the original Kraken run
+
+-----
+
+**Output**
+
+The output of kraken-report is tab-delimited, with one line per taxon. The fields of the output, from left-to-right, are as follows::
+
+ 1. Percentage of reads covered by the clade rooted at this taxon
+ 2. Number of reads covered by the clade rooted at this taxon
+ 3. Number of reads assigned directly to this taxon
+ 4. A rank code, indicating (U)nclassified, (D)omain, (K)ingdom, (P)hylum, (C)lass, (O)rder, (F)amily, (G)enus, or (S)pecies. All other ranks are simply filled with a dash.
+ 5. NCBI taxonomy ID
+ 6. Indented scientific name
+
+The scientific names are indented using spaces, according to the tree
+structure specified by the taxonomy.
+    ]]>
+    </help>
+    <expand macro="version_command" />
+    <expand macro="requirements" />
+    <expand macro="stdio" />
+    <expand macro="citations" />
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Thu Jul 23 10:56:14 2015 -0400
@@ -0,0 +1,30 @@
+<?xml version="1.0"?>
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="0.10.5">kraken</requirement>
+        </requirements>
+    </xml>
+    <xml name="stdio">
+        <stdio>
+            <exit_code description="Tool exception" level="fatal" range="1:" />
+        </stdio>
+    </xml>
+    <xml name="version_command">
+        <version_command>export LC_ALL=C &amp;&amp; kraken --version</version_command>
+    </xml>
+    <xml name="input_database">
+        <param label="Select a Kraken database" name="kraken_database" type="select">
+            <options from_data_table="kraken_databases">
+                <validator message="No databases are available built-in" type="no_options" />
+            </options>
+        </param>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1186/gb-2014-15-3-r46</citation>
+        </citations>
+    </xml>
+    <token name="@INPUT_DATABASE@">--db ${kraken_database.fields.name}</token>
+    <token name="@SET_DATABASE_PATH@">export KRAKEN_DB_PATH="${kraken_database.fields.path}"</token>
+</macros>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Thu Jul 23 10:56:14 2015 -0400
@@ -0,0 +1,8 @@
+<?xml version="1.0"?>
+<tables>
+    <!-- Locations of Kraken database in the required format -->
+    <table name="kraken_databases" comment_char="#">
+        <columns>value, name, path</columns>
+        <file path="tool-data/kraken_databases.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Thu Jul 23 10:56:14 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="kraken" version="0.10.5">
+      <repository changeset_revision="89a36b0f718c" name="package_kraken_0_10_5" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>